The Titanic dataset is composed by two groups:
All numerical variables are going to be analysed taking into consideration the survived column. The categorical variables will be evaluated in terms of relevance for the percentage of survived people.
In this section only numeric variables are presented and its impact on the survived status is preliminary evaluated.
In this section a simple classification model is run in order to evaluate the variables that increases the most the probability of survival.
Survived Predicted N
1: 0 Survived 390
2: 1 Died 194
3: 1 Survived 96
4: 0 Died 34